Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition

Mengke Li, Yiu-ming Cheung*, Yang Lu, Zhikai Hu, Weichao Lan, Hui Huang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

Abstract

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This paper therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. Source code is available at https://github.com/Keke921/GCLLoss.
Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalIEEE Transactions on Artificial Intelligence
DOIs
Publication statusE-pub ahead of print - 15 May 2024

Scopus Subject Areas

  • Artificial Intelligence
  • Computer Science Applications

User-Defined Keywords

  • Imbalance learning
  • long-tailed classification
  • Gaussian clouded logit
  • logit adjustment

Fingerprint

Dive into the research topics of 'Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition'. Together they form a unique fingerprint.

Cite this